© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 30211
    Prev
    Next
    INDEX
    Explanations

    describing capabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     as
    1.55
    ス
    1.30
     are
    1.12
    3
    1.11
    s
    1.05
    ς
    1.05
     Aeonium
    1.04
    с
    1.04
     Manch
    1.02
    AR
    0.98
    POSITIVE LOGITS
    an
    1.33
    ită
    1.16
    ان
    1.05
    ط
    0.98
    ৯
    0.95
    தி
    0.93
    र्तन
    0.90
    for
    0.88
    り
    0.85
     capabilities
    0.84
    Activations Density 0.010%

    No Known Activations